- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- page = self._download_webpage(url, video_id)
-
- title = self._html_search_meta('title', page, 'title')
- description = self._html_search_meta('description', page, 'description')
- thumbnail = self._html_search_regex(r'data-posterimage="([^"]+)"', page, 'thumbnail', fatal=False)
- upload_date = unified_strdate(self._html_search_meta('rightsfrom', page, 'upload date', fatal=False))
- duration = float_or_none(
- self._html_search_regex(r'data-duration="([^"]+)"', page, 'duration', fatal=False))
-
- formats = []
-
- f4m_url = re.search(r'data-media="([^"]+)"', page)
- if f4m_url:
- formats.append({
- 'url': f4m_url.group(1) + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
- 'format_id': 'f4m',
- 'ext': 'flv',
- })
-
- m3u8_url = re.search(r'data-hls-media="([^"]+)"', page)
- if m3u8_url:
- formats.append({
- 'url': m3u8_url.group(1),
- 'format_id': 'm3u8',
- })
-
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'upload_date': upload_date,
- 'duration': duration,
- 'formats': formats,
- }
+ playlist_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = [
+ self.url_result('nrk:%s' % video_id, NRKIE.ie_key())
+ for video_id in re.findall(self._ITEM_RE, webpage)
+ ]
+
+ playlist_title = self. _extract_title(webpage)
+ playlist_description = self._extract_description(webpage)
+
+ return self.playlist_result(
+ entries, playlist_id, playlist_title, playlist_description)
+
+
+class NRKPlaylistIE(NRKPlaylistBaseIE):
+ _VALID_URL = r'https?://(?:www\.)?nrk\.no/(?!video|skole)(?:[^/]+/)+(?P<id>[^/]+)'
+ _ITEM_RE = r'class="[^"]*\brich\b[^"]*"[^>]+data-video-id="([^"]+)"'
+ _TESTS = [{
+ 'url': 'http://www.nrk.no/troms/gjenopplev-den-historiske-solformorkelsen-1.12270763',
+ 'info_dict': {
+ 'id': 'gjenopplev-den-historiske-solformorkelsen-1.12270763',
+ 'title': 'Gjenopplev den historiske solformørkelsen',
+ 'description': 'md5:c2df8ea3bac5654a26fc2834a542feed',
+ },
+ 'playlist_count': 2,
+ }, {
+ 'url': 'http://www.nrk.no/kultur/bok/rivertonprisen-til-karin-fossum-1.12266449',
+ 'info_dict': {
+ 'id': 'rivertonprisen-til-karin-fossum-1.12266449',
+ 'title': 'Rivertonprisen til Karin Fossum',
+ 'description': 'Første kvinne på 15 år til å vinne krimlitteraturprisen.',
+ },
+ 'playlist_count': 5,
+ }]
+
+ def _extract_title(self, webpage):
+ return self._og_search_title(webpage, fatal=False)
+
+ def _extract_description(self, webpage):
+ return self._og_search_description(webpage)
+
+
+class NRKTVEpisodesIE(NRKPlaylistBaseIE):
+ _VALID_URL = r'https?://tv\.nrk\.no/program/[Ee]pisodes/[^/]+/(?P<id>\d+)'
+ _ITEM_RE = r'data-episode=["\']%s' % NRKTVIE._EPISODE_RE
+ _TESTS = [{
+ 'url': 'https://tv.nrk.no/program/episodes/nytt-paa-nytt/69031',
+ 'info_dict': {
+ 'id': '69031',
+ 'title': 'Nytt på nytt, sesong: 201210',
+ },
+ 'playlist_count': 4,
+ }]
+
+ def _extract_title(self, webpage):
+ return self._html_search_regex(
+ r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
+
+
+class NRKTVSeriesIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:tv|radio)\.nrk(?:super)?\.no/serie/(?P<id>[^/]+)'
+ _ITEM_RE = r'(?:data-season=["\']|id=["\']season-)(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'https://tv.nrk.no/serie/groenn-glede',
+ 'info_dict': {
+ 'id': 'groenn-glede',
+ 'title': 'Grønn glede',
+ 'description': 'md5:7576e92ae7f65da6993cf90ee29e4608',
+ },
+ 'playlist_mincount': 9,
+ }, {
+ 'url': 'http://tv.nrksuper.no/serie/labyrint',
+ 'info_dict': {
+ 'id': 'labyrint',
+ 'title': 'Labyrint',
+ 'description': 'md5:58afd450974c89e27d5a19212eee7115',
+ },
+ 'playlist_mincount': 3,
+ }, {
+ 'url': 'https://tv.nrk.no/serie/broedrene-dal-og-spektralsteinene',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://tv.nrk.no/serie/saving-the-human-race',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://tv.nrk.no/serie/postmann-pat',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def suitable(cls, url):
+ return False if NRKTVIE.suitable(url) else super(NRKTVSeriesIE, cls).suitable(url)
+
+ def _real_extract(self, url):
+ series_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, series_id)
+
+ entries = [
+ self.url_result(
+ 'https://tv.nrk.no/program/Episodes/{series}/{season}'.format(
+ series=series_id, season=season_id))
+ for season_id in re.findall(self._ITEM_RE, webpage)
+ ]
+
+ title = self._html_search_meta(
+ 'seriestitle', webpage,
+ 'title', default=None) or self._og_search_title(
+ webpage, fatal=False)
+
+ description = self._html_search_meta(
+ 'series_description', webpage,
+ 'description', default=None) or self._og_search_description(webpage)
+
+ return self.playlist_result(entries, series_id, title, description)
+
+
+class NRKSkoleIE(InfoExtractor):
+ IE_DESC = 'NRK Skole'
+ _VALID_URL = r'https?://(?:www\.)?nrk\.no/skole/?\?.*\bmediaId=(?P<id>\d+)'
+
+ _TESTS = [{
+ 'url': 'https://www.nrk.no/skole/?page=search&q=&mediaId=14099',
+ 'md5': '6bc936b01f9dd8ed45bc58b252b2d9b6',
+ 'info_dict': {
+ 'id': '6021',
+ 'ext': 'mp4',
+ 'title': 'Genetikk og eneggede tvillinger',
+ 'description': 'md5:3aca25dcf38ec30f0363428d2b265f8d',
+ 'duration': 399,
+ },
+ }, {
+ 'url': 'https://www.nrk.no/skole/?page=objectives&subject=naturfag&objective=K15114&mediaId=19355',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ 'https://mimir.nrk.no/plugin/1.0/static?mediaId=%s' % video_id,
+ video_id)
+
+ nrk_id = self._parse_json(
+ self._search_regex(
+ r'<script[^>]+type=["\']application/json["\'][^>]*>({.+?})</script>',
+ webpage, 'application json'),
+ video_id)['activeMedia']['psId']
+
+ return self.url_result('nrk:%s' % nrk_id)
Rapsys Git / youtubedl / blobdiff